Hao Han comments

Results 7 comments of


                                            Hao Han

The resampling preprocessing makes the originally consistent image parameters data.shape, spacing': array inconsistent.

After preprocessed , I noticed that the training time is quite long while using the code they recommended. Have you experienced similar issues with long training times when using MedNext?...

能在windows上复现吗，安装causal-conv1d==1.1.1会报错怎么解决

Hello, I use BRaTS2021 dataset under the 16g memory of the graphics card.Have you delt with it? Thanks！

Would like to save each label as a separate .nii.gz file during the inference phase？

I want to remove the softmax layer from the end of the network during the inference phase and output the probabilities of a voxel belonging to different labels.Thanks！

Would like to save each label as a separate .nii.gz file during the inference phase？

What I'm wondering is whether the .npz file saved by --save_probabilties contains the un-normalized predicted values of the image before it goes through the softmax layer? I'd like to get...

Would like to save each label as a separate .nii.gz file during the inference phase？

As a noob, do I need to modify the network framework at train, and which class under the py file in the reasoning folder should I modify? Thanks!

TypeError: causal_conv1d_fwd(): incompatible function arguments. The following argument types are supported: 1. (arg0: torch.Tensor, arg1: torch.Tensor, arg2: Optional[torch.Tensor], arg3: Optional[torch.Tensor], arg4: bool) -> torch.Tensor

I also get the same problem,did you solve the problem? Can you share your solution?

How to change the batch size and the number of epochs when training?

Have you solved this problem? I would like to know the reason why we "add a new class with the number of X epochs in nnunettrainer_Xepochs, and replace the nnunettrainer...